Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the destructiveHint/idempotentHint annotations: it discloses that this is a soft-delete affecting normal reads, that participant links break, that there is no public restore endpoint, and that uploaded assets may have separate retention. These are exactly the consequences an agent needs before calling a destructive tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.